International Workshop on Spoken Language Translation (IWSLT) 2008 Honolulu, Hawaii, USA October 20-21, 2008

The NICT/ATR Speech Translation System for IWSLT 2008

Masao Utiyama (1), Andrew Finch (1,2), Hideo Okuma (1,2), Michael Paul (1,2), Hailong Cao (1), Hirofumi Yamamoto (1,2), Keiji Yasuda (1,2), Eiichiro Sumita (1,2)

(1) National Institute of Information and Communications Technology
(2) Advanced Telecommunications Research Laboratories
Keihanna Science City, Kyoto, Japan

This paper describes the National Institute of Information and Communications Technology/Advanced Telecommunications Research Institute International (NICT/ATR) statistical machine translation (SMT) system used for the IWSLT 2008 evaluation campaign. We participated in the Chinese– English (Challenge Task), English–Chinese (Challenge Task), Chinese–English (BTEC Task), Chinese–Spanish (BTEC Task), and Chinese–English–Spanish (PIVOT Task) translation tasks. In the English–Chinese translation Challenge Task, we focused on exploring various factors for the English–Chinese translation because the research on the translation of English–Chinese is scarce compared to the opposite direction. In the Chinese–English translation Challenge Task, we employed a novel clustering method, where training sentences similar to the development data in terms of the word error rate formed a cluster. In the pivot translation task, we integrated two strategies for pivot translation by linear interpolation.

Full Paper     Presentation (pdf)

Bibliographic reference.  Utiyama, Masao / Finch, Andrew / Okuma, Hideo / Paul, Michael / Cao, Hailong / Yamamoto, Hirofumi / Yasuda, Keiji / Sumita, Eiichiro (2008): "The NICT/ATR speech translation system for IWSLT 2008", In IWSLT-2008, 77-84.